© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 16462
    Prev
    Next
    INDEX
    Explanations

    the name "En" at various activations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    746
    +0.12
    0.6%
    59
    +0.12
    0.6%
    659
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    746
    +0.12
    0.02
    59
    +0.12
    0.02
    211
    +0.10
    0.01
    Negative Logits
     distortion
    -0.67
     Heights
    -0.65
     independently
    -0.63
     hitch
    -0.61
    ij士
    -0.60
    UGH
    -0.59
    sburgh
    -0.59
     Internal
    -0.59
     methane
    -0.59
     Palmer
    -0.58
    POSITIVE LOGITS
    viron
    1.31
    chanted
    1.19
    rollment
    1.16
    closure
    1.15
    closed
    1.14
    riched
    1.10
    zyme
    1.09
    raged
    1.05
    cyclop
    1.05
    semble
    1.05
    Activations Density 0.010%

    No Known Activations